Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 138 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8250. Min Act: -0.0002

Data Index: 878631 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8118. Min Act: -0.0003

Data Index: 391194 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7872. Min Act: -0.0002

Data Index: 288382 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7131. Min Act: -0.0002

Data Index: 961018 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7414. Min Act: -0.0002

Data Index: 16026 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7869. Min Act: -0.0002

Data Index: 997023 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8201. Min Act: -0.0002

Data Index: 636952 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7596. Min Act: -0.0002

Data Index: 1016219 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.6587. Min Act: -0.0002

Data Index: 1298116 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7733. Min Act: -0.0002

Data Index: 750196 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7871. Min Act: -0.0002

Data Index: 980801 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7659. Min Act: -0.0002

Data Index: 89515 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.8188. Min Act: -0.0002

Data Index: 526609 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7509. Min Act: -0.0002

Data Index: 849359 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7376. Min Act: -0.0002

Data Index: 946808 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7656. Min Act: -0.0002

Data Index: 491756 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7498. Min Act: -0.0002

Data Index: 673960 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7823. Min Act: -0.0002

Data Index: 57991 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7514. Min Act: -0.0002

Data Index: 177911 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.8250. Min Range: -0.8250

Max Act: 0.7584. Min Act: -0.0002

Data Index: 1032499 (C4 (Web Text))

Max Activating Token Index: 270